{ "access": { "embargo": { "active": false, "reason": null }, "files": "public", "record": "public", "status": "open" }, "created": "2018-02-14T19:35:08.002728+00:00", "custom_fields": {}, "deletion_status": { "is_deleted": false, "status": "P" }, "files": { "count": 1, "enabled": true, "entries": { "vtreat.pdf": { "checksum": "md5:12877eceb9f09ea567b3d9f884905d7c", "ext": "pdf", "id": "44702a9d-f822-4fc2-bdb6-cb05ca79c984", "key": "vtreat.pdf", "metadata": null, "mimetype": "application/pdf", "size": 547935 } }, "order": [], "total_bytes": 547935 }, "id": "1173314", "is_draft": false, "is_published": true, "links": { "access": "https://zenodo.org/api/records/1173314/access", "access_links": "https://zenodo.org/api/records/1173314/access/links", "access_request": "https://zenodo.org/api/records/1173314/access/request", "access_users": "https://zenodo.org/api/records/1173314/access/users", "archive": "https://zenodo.org/api/records/1173314/files-archive", "archive_media": "https://zenodo.org/api/records/1173314/media-files-archive", "communities": "https://zenodo.org/api/records/1173314/communities", "communities-suggestions": "https://zenodo.org/api/records/1173314/communities-suggestions", "doi": "https://doi.org/10.5281/zenodo.1173314", "draft": "https://zenodo.org/api/records/1173314/draft", "files": "https://zenodo.org/api/records/1173314/files", "latest": "https://zenodo.org/api/records/1173314/versions/latest", "latest_html": "https://zenodo.org/records/1173314/latest", "media_files": "https://zenodo.org/api/records/1173314/media-files", "parent": "https://zenodo.org/api/records/1173313", "parent_doi": "https://zenodo.org/doi/10.5281/zenodo.1173313", "parent_html": "https://zenodo.org/records/1173313", "requests": "https://zenodo.org/api/records/1173314/requests", "reserve_doi": "https://zenodo.org/api/records/1173314/draft/pids/doi", "self": "https://zenodo.org/api/records/1173314", "self_doi": "https://zenodo.org/doi/10.5281/zenodo.1173314", "self_html": "https://zenodo.org/records/1173314", "self_iiif_manifest": "https://zenodo.org/api/iiif/record:1173314/manifest", "self_iiif_sequence": "https://zenodo.org/api/iiif/record:1173314/sequence/default", "versions": "https://zenodo.org/api/records/1173314/versions" }, "media_files": { "count": 0, "enabled": false, "entries": {}, "order": [], "total_bytes": 0 }, "metadata": { "creators": [ { "affiliations": [ { "name": "Win-Vector LLC" } ], "person_or_org": { "family_name": "Zumel", "given_name": "Nina", "identifiers": [ { "identifier": "0000-0001-8831-0190", "scheme": "orcid" } ], "name": "Zumel, Nina", "type": "personal" } }, { "affiliations": [ { "name": "Win-Vector LLC" } ], "person_or_org": { "family_name": "Mount", "given_name": "John", "identifiers": [ { "identifier": "0000-0002-3696-2012", "scheme": "orcid" } ], "name": "Mount, John", "type": "personal" } } ], "description": "
We look at common problems found in data that is used for predictive modeling tasks, and describe how to address them with the vtreat R package. vtreat prepares real-world data for predictive modeling in a reproducible and statistically sound manner. We describe the theory of preparing variables so that data has fewer exceptional cases, making it easier to safely use models in production. Common problems dealt with include: infinite values, invalid values, NA, too many categorical levels, rare categorical levels, and new categorical levels (levels seen during application, but not during training). Of special interest are techniques needed to avoid needlessly introducing undesirable nested modeling bias (which is a risk when using a data-preprocessor).
", "languages": [ { "id": "eng", "title": { "en": "English" } } ], "publication_date": "2016-11-29", "publisher": "Zenodo", "resource_type": { "id": "publication-preprint", "title": { "de": "Preprint", "en": "Preprint" } }, "rights": [ { "description": { "en": "The Creative Commons Attribution license allows re-distribution and re-use of a licensed work on the condition that the creator is appropriately credited." }, "icon": "cc-by-icon", "id": "cc-by-4.0", "props": { "scheme": "spdx", "url": "https://creativecommons.org/licenses/by/4.0/legalcode" }, "title": { "en": "Creative Commons Attribution 4.0 International" } } ], "title": "vtreat: a data.frame Processor for Predictive Modeling" }, "parent": { "access": { "owned_by": { "user": 42188 } }, "communities": {}, "id": "1173313", "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.1173313", "provider": "datacite" } } }, "pids": { "doi": { "client": "datacite", "identifier": "10.5281/zenodo.1173314", "provider": "datacite" }, "oai": { "identifier": "oai:zenodo.org:1173314", "provider": "oai" } }, "revision_id": 7, "stats": { "all_versions": { "data_volume": 147160127.0, "downloads": 277, "unique_downloads": 257, "unique_views": 760, "views": 867 }, "this_version": { "data_volume": 39999255.0, "downloads": 73, "unique_downloads": 71, "unique_views": 237, "views": 247 } }, "status": "published", "updated": "2020-01-20T17:14:05.198973+00:00", "versions": { "index": 1, "is_latest": false } }